def get_targets(self, points, gt_bboxes_list, gt_labels_list):
"""Compute regression, classification and centerss targets for points
in multiple images.
Args:
points (list[Tensor]): Points of each fpn level, each has shape
(num_points, 2).
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image,
each has shape (num_gt, 4).
gt_labels_list (list[Tensor]): Ground truth labels of each box,
each has shape (num_gt,).
Returns:
tuple:
concat_lvl_labels (list[Tensor]): Labels of each level. \
concat_lvl_bbox_targets (list[Tensor]): BBox targets of each \
level.
"""
assert len(points) == len(self.regress_ranges)
num_levels = len(points)
# expand regress ranges to align with points
expanded_regress_ranges = [
points[i].new_tensor(self.regress_ranges[i])[None].expand_as(
points[i]) for i in range(num_levels)
]
# concat all levels points and regress ranges
concat_regress_ranges = torch.cat(expanded_regress_ranges, dim=0)
concat_points = torch.cat(points, dim=0)
# the number of points per img, per lvl
num_points = [center.size(0) for center in points]
# get labels and bbox_targets of each image
labels_list, bbox_targets_list = multi_apply(
self._get_target_single,
gt_bboxes_list,
gt_labels_list,
points=concat_points,
regress_ranges=concat_regress_ranges,
num_points_per_lvl=num_points)
# split to per img, per level
labels_list = [labels.split(num_points, 0) for labels in labels_list]
bbox_targets_list = [
bbox_targets.split(num_points, 0)
for bbox_targets in bbox_targets_list
]
# concat per level image
concat_lvl_labels = []
concat_lvl_bbox_targets = []
for i in range(num_levels):
concat_lvl_labels.append(
torch.cat([labels[i] for labels in labels_list]))
bbox_targets = torch.cat(
[bbox_targets[i] for bbox_targets in bbox_targets_list])
if self.norm_on_bbox:
bbox_targets = bbox_targets / self.strides[i]
concat_lvl_bbox_targets.append(bbox_targets)
return concat_lvl_labels, concat_lvl_bbox_targets
def bucket_target(self,
pos_proposals_list,
neg_proposals_list,
pos_gt_bboxes_list,
pos_gt_labels_list,
rcnn_train_cfg,
concat=True):
(labels, label_weights, bucket_cls_targets, bucket_cls_weights,
bucket_offset_targets,
bucket_offset_weights) = multi_apply(self._bucket_target_single,
pos_proposals_list,
neg_proposals_list,
pos_gt_bboxes_list,
pos_gt_labels_list,
cfg=rcnn_train_cfg)
if concat:
labels = torch.cat(labels, 0)
label_weights = torch.cat(label_weights, 0)
bucket_cls_targets = torch.cat(bucket_cls_targets, 0)
bucket_cls_weights = torch.cat(bucket_cls_weights, 0)
bucket_offset_targets = torch.cat(bucket_offset_targets, 0)
bucket_offset_weights = torch.cat(bucket_offset_weights, 0)
return (labels, label_weights, bucket_cls_targets, bucket_cls_weights,
bucket_offset_targets, bucket_offset_weights)
def forward(self, feats):
"""Forward features from the upstream network.
Args:
feats (tuple[Tensor]): Features from the upstream network, each is
a 4D-tensor.
Returns:
tuple: Usually a tuple of corner heatmaps, offset heatmaps and
embedding heatmaps.
- tl_heats (list[Tensor]): Top-left corner heatmaps for all
levels, each is a 4D-tensor, the channels number is
num_classes.
- br_heats (list[Tensor]): Bottom-right corner heatmaps for all
levels, each is a 4D-tensor, the channels number is
num_classes.
- tl_embs (list[Tensor] | list[None]): Top-left embedding
heatmaps for all levels, each is a 4D-tensor or None.
If not None, the channels number is corner_emb_channels.
- br_embs (list[Tensor] | list[None]): Bottom-right embedding
heatmaps for all levels, each is a 4D-tensor or None.
If not None, the channels number is corner_emb_channels.
- tl_offs (list[Tensor]): Top-left offset heatmaps for all
levels, each is a 4D-tensor. The channels number is
corner_offset_channels.
- br_offs (list[Tensor]): Bottom-right offset heatmaps for all
levels, each is a 4D-tensor. The channels number is
corner_offset_channels.
"""
lvl_ind = list(range(self.num_feat_levels))
return multi_apply(self.forward_single, feats, lvl_ind)
def loss(self,
tl_heats,
br_heats,
tl_embs,
br_embs,
tl_offs,
br_offs,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute losses of the head.
Args:
tl_heats (list[Tensor]): Top-left corner heatmaps for each level
with shape (N, num_classes, H, W).
br_heats (list[Tensor]): Bottom-right corner heatmaps for each
level with shape (N, num_classes, H, W).
tl_embs (list[Tensor]): Top-left corner embeddings for each level
with shape (N, corner_emb_channels, H, W).
br_embs (list[Tensor]): Bottom-right corner embeddings for each
level with shape (N, corner_emb_channels, H, W).
tl_offs (list[Tensor]): Top-left corner offsets for each level
with shape (N, corner_offset_channels, H, W).
br_offs (list[Tensor]): Bottom-right corner offsets for each level
with shape (N, corner_offset_channels, H, W).
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 4) in [left, top, right, bottom] format.
gt_labels (list[Tensor]): Class indices corresponding to each box.
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (list[Tensor] | None): Specify which bounding
boxes can be ignored when computing the loss.
Returns:
dict[str, Tensor]: A dictionary of loss components. Containing the
following losses:
- det_loss (list[Tensor]): Corner keypoint losses of all
feature levels.
- pull_loss (list[Tensor]): Part one of AssociativeEmbedding
losses of all feature levels.
- push_loss (list[Tensor]): Part two of AssociativeEmbedding
losses of all feature levels.
- off_loss (list[Tensor]): Corner offset losses of all feature
levels.
"""
targets = self.get_targets(gt_bboxes,
gt_labels,
tl_heats[-1].shape,
img_metas[0]['pad_shape'],
with_corner_emb=self.with_corner_emb)
mlvl_targets = [targets for _ in range(self.num_feat_levels)]
det_losses, pull_losses, push_losses, off_losses = multi_apply(
self.loss_single, tl_heats, br_heats, tl_embs, br_embs, tl_offs,
br_offs, mlvl_targets)
loss_dict = dict(det_loss=det_losses, off_loss=off_losses)
if self.with_corner_emb:
loss_dict.update(pull_loss=pull_losses, push_loss=push_losses)
return loss_dict
def loss(self,
cls_scores,
bbox_preds,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == self.approx_anchor_generator.num_levels
device = cls_scores[0].device
# get sampled approxes
approxs_list, inside_flag_list = GuidedAnchorHead.get_sampled_approxs(
self, featmap_sizes, img_metas, device=device)
square_list = self.get_anchors(featmap_sizes, img_metas, device=device)
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
cls_reg_targets = self.get_target(
approxs_list,
inside_flag_list,
square_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels,
sampling=self.sampling)
if cls_reg_targets is None:
return None
(labels_list, label_weights_list, bbox_cls_targets_list,
bbox_cls_weights_list, bbox_reg_targets_list, bbox_reg_weights_list,
num_total_pos, num_total_neg) = cls_reg_targets
num_total_samples = (num_total_pos +
num_total_neg if self.sampling else num_total_pos)
losses_cls, losses_bbox_cls, losses_bbox_reg = multi_apply(
self.loss_single,
cls_scores,
bbox_preds,
labels_list,
label_weights_list,
bbox_cls_targets_list,
bbox_cls_weights_list,
bbox_reg_targets_list,
bbox_reg_weights_list,
num_total_samples=num_total_samples)
return dict(loss_cls=losses_cls,
loss_bbox_cls=losses_bbox_cls,
loss_bbox_reg=losses_bbox_reg)
def loss(self,
pred_maps,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute loss of the head.
Args:
pred_maps (list[Tensor]): Prediction map for each scale level,
shape (N, num_anchors * num_attrib, H, W)
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (None | list[Tensor]): specify which bounding
boxes can be ignored when computing the loss.
Returns:
dict[str, Tensor]: A dictionary of loss components.
"""
num_imgs = len(img_metas)
device = pred_maps[0][0].device
featmap_sizes = [
pred_maps[i].shape[-2:] for i in range(self.num_levels)
]
multi_level_anchors = self.anchor_generator.grid_anchors(
featmap_sizes, device)
anchor_list = [multi_level_anchors for _ in range(num_imgs)]
responsible_flag_list = []
for img_id in range(len(img_metas)):
# 计算当前图片中的bbox中心在特征图上面的位置,以flag形式表示
responsible_flag_list.append(
self.anchor_generator.responsible_flags(
featmap_sizes, gt_bboxes[img_id], device))
target_maps_list, neg_maps_list = self.get_targets(
anchor_list, responsible_flag_list, gt_bboxes, gt_labels,
img_metas)
losses_cls, losses_conf, losses_xy, losses_wh = multi_apply(
self.loss_single, pred_maps, target_maps_list, neg_maps_list)
return dict(loss_cls=losses_cls,
loss_conf=losses_conf,
loss_xy=losses_xy,
loss_wh=losses_wh)
def forward(self, feats):
"""Forward features from the upstream network.
Args:
feats (tuple[Tensor]): Features from the upstream network, each is
a 4D-tensor.
Returns:
tuple: Usually a tuple of classification scores and bbox prediction
cls_scores (list[Tensor]): Classification scores for all scale
levels, each is a 4D-tensor, the channels number is
num_anchors * num_classes.
bbox_preds (list[Tensor]): Box energies / deltas for all scale
levels, each is a 4D-tensor, the channels number is
num_anchors * 4.
"""
return multi_apply(self.forward_single, feats, self.scales)
def forward(self, feats):
"""Forward features from the upstream network.
Args:
feats (tuple[Tensor]): Features from the upstream network, each is
a 4D-tensor.
Returns:
tuple: Usually a tuple of classification scores and bbox prediction
cls_scores (list[Tensor]): Classification and quality (IoU)
joint scores for all scale levels, each is a 4D-tensor,
the channel number is num_classes.
bbox_preds (list[Tensor]): Box distribution logits for all
scale levels, each is a 4D-tensor, the channel number is
4*(n+1), n is max value of integral set.
"""
return multi_apply(self.forward_single, feats, self.scales)
def forward(self, feats):
"""Forward features from the upstream network.
Args:
feats (tuple[Tensor]): Features from the upstream network, each is
a 4D-tensor.
Returns:
tuple: Usually contain classification scores and bbox predictions.
cls_scores (list[Tensor]): Box scores for each scale level,
each is a 4D-tensor, the channel number is
num_points * num_classes.
bbox_preds (list[Tensor]): Box energies / deltas for each scale
level, each is a 4D-tensor, the channel number is
num_points * 4.
"""
return multi_apply(self.forward_single, feats)[:2]
def forward(self, feats):
"""Forward features from the upstream network.
Args:
feats (tuple[Tensor]): Features from the upstream network, each is
a 4D-tensor.
Returns:
tuple:
cls_scores (list[Tensor]): Box scores for each scale level, \
each is a 4D-tensor, the channel number is \
num_points * num_classes.
bbox_preds (list[Tensor]): Box energies / deltas for each \
scale level, each is a 4D-tensor, the channel number is \
num_points * 4.
centernesses (list[Tensor]): Centerss for each scale level, \
each is a 4D-tensor, the channel number is num_points * 1.
"""
return multi_apply(self.forward_single, feats, self.scales,
self.strides)
def forward(self, feats):
"""Forward features from the upstream network.
Args:
feats (tuple[Tensor]): Features from the upstream network, each is
a 4D-tensor.
Returns:
tuple:
cls_scores (list[Tensor]): Box iou-aware scores for each scale
level, each is a 4D-tensor, the channel number is
num_points * num_classes.
bbox_preds (list[Tensor]): Box offsets for each
scale level, each is a 4D-tensor, the channel number is
num_points * 4.
bbox_preds_refine (list[Tensor]): Refined Box offsets for
each scale level, each is a 4D-tensor, the channel
number is num_points * 4.
"""
return multi_apply(self.forward_single, feats, self.scales,
self.scales_refine, self.strides, self.reg_denoms)
def get_targets(self, anchor_list, responsible_flag_list, gt_bboxes_list,
gt_labels_list, img_metas):
"""Compute target maps for anchors in multiple images.
Args:
anchor_list (list[list[Tensor]]): Multi level anchors of each
image. The outer list indicates images, and the inner list
corresponds to feature levels of the image. Each element of
the inner list is a tensor of shape (num_total_anchors, 4).
responsible_flag_list (list[list[Tensor]]): Multi level responsible
flags of each image. Each element is a tensor of shape
(num_total_anchors, )
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
gt_labels_list (list[Tensor]): Ground truth labels of each box.
Returns:
tuple: Usually returns a tuple containing learning targets.
- target_map_list (list[Tensor]): Target map of each level.
- neg_map_list (list[Tensor]): Negative map of each level.
"""
num_imgs = len(anchor_list)
# anchor number of multi levels 每一层anchor的个数，例如输出是10x10，那么10x10x3=300
num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]]
results = multi_apply(self._get_targets_single,
anchor_list,
responsible_flag_list,
gt_bboxes_list,
gt_labels_list,
img_metas,
num_level_anchors=num_level_anchors)
all_target_maps, all_neg_maps = results
assert num_imgs == len(all_target_maps) == len(all_neg_maps)
# all_target_maps是图片级别list结构，假设有8张图片则len()=8，需要转化为fpn级别的输出，才方便计算Loss,假设有三层输出，则len()=3
target_maps_list = images_to_levels(all_target_maps, num_level_anchors)
neg_maps_list = images_to_levels(all_neg_maps, num_level_anchors)
return target_maps_list, neg_maps_list
def get_targets(self,
sampling_results,
gt_bboxes,
gt_labels,
rcnn_train_cfg,
concat=True):
pos_bboxes_list = [res.pos_bboxes for res in sampling_results]
neg_bboxes_list = [res.neg_bboxes for res in sampling_results]
pos_gt_bboxes_list = [res.pos_gt_bboxes for res in sampling_results]
pos_gt_labels_list = [res.pos_gt_labels for res in sampling_results]
labels, label_weights, bbox_targets, bbox_weights = multi_apply(
self._get_target_single,
pos_bboxes_list,
neg_bboxes_list,
pos_gt_bboxes_list,
pos_gt_labels_list,
cfg=rcnn_train_cfg)
if concat:
labels = torch.cat(labels, 0)
label_weights = torch.cat(label_weights, 0)
bbox_targets = torch.cat(bbox_targets, 0)
bbox_weights = torch.cat(bbox_weights, 0)
return labels, label_weights, bbox_targets, bbox_weights
def loss(self,
cls_scores,
bbox_preds,
shape_preds,
loc_preds,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == self.approx_anchor_generator.num_levels
device = cls_scores[0].device
# get loc targets
loc_targets, loc_weights, loc_avg_factor = self.ga_loc_targets(
gt_bboxes, featmap_sizes)
# anchor的shape预测分支所需要的anchor_list
approxs_list, inside_flag_list = self.get_sampled_approxs(
featmap_sizes, img_metas, device=device)
# 利用anchor生成分支得到guided_anchors(稀疏值),用于后续训练原始分类和回归分支
# 但是作者设置use_loc_filter=False，也就是对loc分支预测值不过滤
# squares_list长度和guided_anchors_list一样，可能是为了使得focal loss的参数不需要改变才这么设置吧
squares_list, guided_anchors_list, _ = self.get_anchors(featmap_sizes,
shape_preds,
loc_preds,
img_metas,
device=device)
# get shape targets
shape_targets = self.ga_shape_targets(approxs_list, inside_flag_list,
squares_list, gt_bboxes,
img_metas)
if shape_targets is None:
return None
# bbox_anchors_list就是squares_list
(bbox_anchors_list, bbox_gts_list, anchor_weights_list, anchor_fg_num,
anchor_bg_num) = shape_targets
anchor_total_num = (anchor_fg_num if not self.ga_sampling else
anchor_fg_num + anchor_bg_num)
# get anchor targets
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
# 原始分支的target计算，比较简单
# 需要注意的是如果guided_anchors_list是稀疏的，而且很多iou应该大于0.5,也就是此时该分支训练时候很多都是正样本
# 不平衡问题应该没有原来严重了，但是这里设置依然是密集的
cls_reg_targets = self.get_targets(
guided_anchors_list,
inside_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels)
if cls_reg_targets is None:
return None
(labels_list, label_weights_list, bbox_targets_list, bbox_weights_list,
num_total_pos, num_total_neg) = cls_reg_targets
num_total_samples = (num_total_pos +
num_total_neg if self.sampling else num_total_pos)
# anchor number of multi levels
num_level_anchors = [
anchors.size(0) for anchors in guided_anchors_list[0]
]
# concat all level anchors to a single tensor
concat_anchor_list = []
for i in range(len(guided_anchors_list)):
concat_anchor_list.append(torch.cat(guided_anchors_list[i]))
all_anchor_list = images_to_levels(concat_anchor_list,
num_level_anchors)
# get classification and bbox regression losses
# 原始分类和回归分支，和原来一样
losses_cls, losses_bbox = multi_apply(
self.loss_single,
cls_scores,
bbox_preds,
all_anchor_list,
labels_list,
label_weights_list,
bbox_targets_list,
bbox_weights_list,
num_total_samples=num_total_samples)
# get anchor location loss
losses_loc = []
for i in range(len(loc_preds)):
loss_loc = self.loss_loc_single(loc_preds[i],
loc_targets[i],
loc_weights[i],
loc_avg_factor=loc_avg_factor)
losses_loc.append(loss_loc)
# get anchor shape loss
losses_shape = []
for i in range(len(shape_preds)):
loss_shape = self.loss_shape_single(
shape_preds[i],
bbox_anchors_list[i],
bbox_gts_list[i],
anchor_weights_list[i],
anchor_total_num=anchor_total_num)
losses_shape.append(loss_shape)
return dict(loss_cls=losses_cls,
loss_bbox=losses_bbox,
loss_shape=losses_shape,
loss_loc=losses_loc)
def ga_shape_targets(self,
approx_list,
inside_flag_list,
square_list,
gt_bboxes_list,
img_metas,
gt_bboxes_ignore_list=None,
unmap_outputs=True):
"""Compute guided anchoring targets.
Args:
approx_list (list[list]): Multi level approxs of each image.
inside_flag_list (list[list]): Multi level inside flags of each
image.
square_list (list[list]): Multi level squares of each image.
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
img_metas (list[dict]): Meta info of each image.
gt_bboxes_ignore_list (list[Tensor]): ignore list of gt bboxes.
unmap_outputs (bool): unmap outputs or not.
Returns:
tuple
"""
num_imgs = len(img_metas)
assert len(approx_list) == len(inside_flag_list) == len(
square_list) == num_imgs
# anchor number of multi levels
num_level_squares = [squares.size(0) for squares in square_list[0]]
# concat all level anchors and flags to a single tensor
inside_flag_flat_list = []
approx_flat_list = []
square_flat_list = []
for i in range(num_imgs):
assert len(square_list[i]) == len(inside_flag_list[i])
inside_flag_flat_list.append(torch.cat(inside_flag_list[i]))
approx_flat_list.append(torch.cat(approx_list[i]))
square_flat_list.append(torch.cat(square_list[i]))
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
(all_bbox_anchors, all_bbox_gts, all_bbox_weights, pos_inds_list,
neg_inds_list) = multi_apply(self._ga_shape_target_single,
approx_flat_list,
inside_flag_flat_list,
square_flat_list,
gt_bboxes_list,
gt_bboxes_ignore_list,
img_metas,
unmap_outputs=unmap_outputs)
# no valid anchors
if any([bbox_anchors is None for bbox_anchors in all_bbox_anchors]):
return None
# sampled anchors of all images
num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list])
num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list])
# split targets to a list w.r.t. multiple levels
bbox_anchors_list = images_to_levels(all_bbox_anchors,
num_level_squares)
bbox_gts_list = images_to_levels(all_bbox_gts, num_level_squares)
bbox_weights_list = images_to_levels(all_bbox_weights,
num_level_squares)
return (bbox_anchors_list, bbox_gts_list, bbox_weights_list,
num_total_pos, num_total_neg)
def forward(self, feats):
return multi_apply(self.forward_single, feats)
def get_target(self,
approx_list,
inside_flag_list,
square_list,
gt_bboxes_list,
img_metas,
gt_bboxes_ignore_list=None,
gt_labels_list=None,
label_channels=None,
sampling=True,
unmap_outputs=True):
"""Compute bucketing targets.
Args:
approx_list (list[list]): Multi level approxs of each image.
inside_flag_list (list[list]): Multi level inside flags of each
image.
square_list (list[list]): Multi level squares of each image.
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
img_metas (list[dict]): Meta info of each image.
gt_bboxes_ignore_list (list[Tensor]): ignore list of gt bboxes.
gt_bboxes_list (list[Tensor]): Gt bboxes of each image.
label_channels (int): Channel of label.
sampling (bool): Sample Anchors or not.
unmap_outputs (bool): unmap outputs or not.
Returns:
tuple: Returns a tuple containing learning targets.
- labels_list (list[Tensor]): Labels of each level.
- label_weights_list (list[Tensor]): Label weights of each \
level.
- bbox_cls_targets_list (list[Tensor]): BBox cls targets of \
each level.
- bbox_cls_weights_list (list[Tensor]): BBox cls weights of \
each level.
- bbox_reg_targets_list (list[Tensor]): BBox reg targets of \
each level.
- bbox_reg_weights_list (list[Tensor]): BBox reg weights of \
each level.
- num_total_pos (int): Number of positive samples in all \
images.
- num_total_neg (int): Number of negative samples in all \
images.
"""
num_imgs = len(img_metas)
assert len(approx_list) == len(inside_flag_list) == len(
square_list) == num_imgs
# anchor number of multi levels
num_level_squares = [squares.size(0) for squares in square_list[0]]
# concat all level anchors and flags to a single tensor
inside_flag_flat_list = []
approx_flat_list = []
square_flat_list = []
for i in range(num_imgs):
assert len(square_list[i]) == len(inside_flag_list[i])
inside_flag_flat_list.append(torch.cat(inside_flag_list[i]))
approx_flat_list.append(torch.cat(approx_list[i]))
square_flat_list.append(torch.cat(square_list[i]))
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
if gt_labels_list is None:
gt_labels_list = [None for _ in range(num_imgs)]
(all_labels, all_label_weights, all_bbox_cls_targets,
all_bbox_cls_weights, all_bbox_reg_targets, all_bbox_reg_weights,
pos_inds_list,
neg_inds_list) = multi_apply(self._get_target_single,
approx_flat_list,
inside_flag_flat_list,
square_flat_list,
gt_bboxes_list,
gt_bboxes_ignore_list,
gt_labels_list,
img_metas,
label_channels=label_channels,
sampling=sampling,
unmap_outputs=unmap_outputs)
# no valid anchors
if any([labels is None for labels in all_labels]):
return None
# sampled anchors of all images
num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list])
num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list])
# split targets to a list w.r.t. multiple levels
labels_list = images_to_levels(all_labels, num_level_squares)
label_weights_list = images_to_levels(all_label_weights,
num_level_squares)
bbox_cls_targets_list = images_to_levels(all_bbox_cls_targets,
num_level_squares)
bbox_cls_weights_list = images_to_levels(all_bbox_cls_weights,
num_level_squares)
bbox_reg_targets_list = images_to_levels(all_bbox_reg_targets,
num_level_squares)
bbox_reg_weights_list = images_to_levels(all_bbox_reg_weights,
num_level_squares)
return (labels_list, label_weights_list, bbox_cls_targets_list,
bbox_cls_weights_list, bbox_reg_targets_list,
bbox_reg_weights_list, num_total_pos, num_total_neg)
def loss(self,
cls_scores,
bbox_preds,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute losses of the head.
Args:
cls_scores (list[Tensor]): Cls and quality scores for each scale
level has shape (N, num_classes, H, W).
bbox_preds (list[Tensor]): Box distribution logits for each scale
level with shape (N, 4*(n+1), H, W), n is max value of integral
set.
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (list[Tensor] | None): specify which bounding
boxes can be ignored when computing the loss.
Returns:
dict[str, Tensor]: A dictionary of loss components.
"""
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == self.anchor_generator.num_levels
device = cls_scores[0].device
anchor_list, valid_flag_list = self.get_anchors(
featmap_sizes, img_metas, device=device)
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
cls_reg_targets = self.get_targets(
anchor_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels)
if cls_reg_targets is None:
return None
(anchor_list, labels_list, label_weights_list, bbox_targets_list,
bbox_weights_list, num_total_pos, num_total_neg) = cls_reg_targets
num_total_samples = num_total_pos
num_total_samples = max(num_total_samples, 1.0)
losses_cls, losses_bbox, losses_dfl, \
avg_factor = multi_apply(
self.loss_single,
anchor_list,
cls_scores,
bbox_preds,
labels_list,
label_weights_list,
bbox_targets_list,
self.anchor_generator.strides,
num_total_samples=num_total_samples)
avg_factor = sum(avg_factor)
avg_factor = avg_factor.item()
losses_bbox = list(map(lambda x: x / avg_factor, losses_bbox))
losses_dfl = list(map(lambda x: x / avg_factor, losses_dfl))
return dict(
loss_cls=losses_cls, loss_bbox=losses_bbox, loss_dfl=losses_dfl)
def get_targets(
self,
anchor_list,
valid_flag_list,
gt_bboxes_list,
img_metas,
gt_bboxes_ignore_list=None,
gt_labels_list=None,
label_channels=1,
unmap_outputs=True,
):
"""Get targets for PAA head.
This method is almost the same as `AnchorHead.get_targets()`. We direct
return the results from _get_targets_single instead map it to levels
by images_to_levels function.
Args:
anchor_list (list[list[Tensor]]): Multi level anchors of each
image. The outer list indicates images, and the inner list
corresponds to feature levels of the image. Each element of
the inner list is a tensor of shape (num_anchors, 4).
valid_flag_list (list[list[Tensor]]): Multi level valid flags of
each image. The outer list indicates images, and the inner list
corresponds to feature levels of the image. Each element of
the inner list is a tensor of shape (num_anchors, )
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
img_metas (list[dict]): Meta info of each image.
gt_bboxes_ignore_list (list[Tensor]): Ground truth bboxes to be
ignored.
gt_labels_list (list[Tensor]): Ground truth labels of each box.
label_channels (int): Channel of label.
unmap_outputs (bool): Whether to map outputs back to the original
set of anchors.
Returns:
tuple: Usually returns a tuple containing learning targets.
- labels (list[Tensor]): Labels of all anchors, each with
shape (num_anchors,).
- label_weights (list[Tensor]): Label weights of all anchor.
each with shape (num_anchors,).
- bbox_targets (list[Tensor]): BBox targets of all anchors.
each with shape (num_anchors, 4).
- bbox_weights (list[Tensor]): BBox weights of all anchors.
each with shape (num_anchors, 4).
- pos_inds (list[Tensor]): Contains all index of positive
sample in all anchor.
- gt_inds (list[Tensor]): Contains all gt_index of positive
sample in all anchor.
"""
num_imgs = len(img_metas)
assert len(anchor_list) == len(valid_flag_list) == num_imgs
concat_anchor_list = []
concat_valid_flag_list = []
for i in range(num_imgs):
assert len(anchor_list[i]) == len(valid_flag_list[i])
concat_anchor_list.append(torch.cat(anchor_list[i]))
concat_valid_flag_list.append(torch.cat(valid_flag_list[i]))
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
if gt_labels_list is None:
gt_labels_list = [None for _ in range(num_imgs)]
results = multi_apply(self._get_targets_single,
concat_anchor_list,
concat_valid_flag_list,
gt_bboxes_list,
gt_bboxes_ignore_list,
gt_labels_list,
img_metas,
label_channels=label_channels,
unmap_outputs=unmap_outputs)
(labels, label_weights, bbox_targets, bbox_weights, valid_pos_inds,
valid_neg_inds, sampling_result) = results
# Due to valid flag of anchors, we have to calculate the real pos_inds
# in origin anchor set.
pos_inds = []
for i, single_labels in enumerate(labels):
pos_mask = (0 <= single_labels) & (single_labels <
self.num_classes)
pos_inds.append(pos_mask.nonzero().view(-1))
gt_inds = [item.pos_assigned_gt_inds for item in sampling_result]
return (labels, label_weights, bbox_targets, bbox_weights, pos_inds,
gt_inds)
def loss(self,
cls_scores,
bbox_preds,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute losses of the head.
Args:
cls_scores (list[Tensor]): Box scores for each scale level
Has shape (N, num_anchors * num_classes, H, W)
bbox_preds (list[Tensor]): Box energies / deltas for each scale
level with shape (N, num_anchors * 4, H, W)
gt_bboxes (list[Tensor]): each item are the truth boxes for each
image in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (None | list[Tensor]): specify which bounding
boxes can be ignored when computing the loss.
Returns:
dict[str, Tensor]: A dictionary of loss components.
"""
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == self.anchor_generator.num_levels
device = cls_scores[0].device
anchor_list, valid_flag_list = self.get_anchors(featmap_sizes,
img_metas,
device=device)
cls_reg_targets = self.get_targets(
anchor_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=1,
unmap_outputs=False)
if cls_reg_targets is None:
return None
(labels_list, label_weights_list, bbox_targets_list, bbox_weights_list,
num_total_pos, num_total_neg) = cls_reg_targets
num_images = len(img_metas)
all_cls_scores = torch.cat([
s.permute(0, 2, 3, 1).reshape(
num_images, -1, self.cls_out_channels) for s in cls_scores
], 1)
all_labels = torch.cat(labels_list, -1).view(num_images, -1)
all_label_weights = torch.cat(label_weights_list,
-1).view(num_images, -1)
all_bbox_preds = torch.cat([
b.permute(0, 2, 3, 1).reshape(num_images, -1, 4)
for b in bbox_preds
], -2)
all_bbox_targets = torch.cat(bbox_targets_list,
-2).view(num_images, -1, 4)
all_bbox_weights = torch.cat(bbox_weights_list,
-2).view(num_images, -1, 4)
# concat all level anchors to a single tensor
all_anchors = []
for i in range(num_images):
all_anchors.append(torch.cat(anchor_list[i]))
# check NaN and Inf
assert torch.isfinite(all_cls_scores).all().item(), \
'classification scores become infinite or NaN!'
assert torch.isfinite(all_bbox_preds).all().item(), \
'bbox predications become infinite or NaN!'
losses_cls, losses_bbox = multi_apply(self.loss_single,
all_cls_scores,
all_bbox_preds,
all_anchors,
all_labels,
all_label_weights,
all_bbox_targets,
all_bbox_weights,
num_total_samples=num_total_pos)
return dict(loss_cls=losses_cls, loss_bbox=losses_bbox)
def get_targets(self,
anchor_list,
valid_flag_list,
gt_bboxes_list,
img_metas,
gt_bboxes_ignore_list=None,
gt_labels_list=None,
label_channels=1,
unmap_outputs=True):
"""Get targets for ATSS head.
This method is almost the same as `AnchorHead.get_targets()`. Besides
returning the targets as the parent method does, it also returns the
anchors as the first element of the returned tuple.
"""
num_imgs = len(img_metas)
assert len(anchor_list) == len(valid_flag_list) == num_imgs
# 调试anchor
# imgs = []
# for an in anchor_list[0]:
# img = show_pos_anchor(img_metas[0], an, gt_bboxes_list[0], is_show=False)
# imgs.append(img)
# cv_core.show_img(imgs)
# anchor number of multi levels
num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]]
num_level_anchors_list = [num_level_anchors] * num_imgs
# concat all level anchors and flags to a single tensor
for i in range(num_imgs):
assert len(anchor_list[i]) == len(valid_flag_list[i])
anchor_list[i] = torch.cat(anchor_list[i])
valid_flag_list[i] = torch.cat(valid_flag_list[i])
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
if gt_labels_list is None:
gt_labels_list = [None for _ in range(num_imgs)]
(all_anchors, all_labels, all_label_weights, all_bbox_targets,
all_bbox_weights, pos_inds_list,
neg_inds_list) = multi_apply(self._get_target_single,
anchor_list,
valid_flag_list,
num_level_anchors_list,
gt_bboxes_list,
gt_bboxes_ignore_list,
gt_labels_list,
img_metas,
label_channels=label_channels,
unmap_outputs=unmap_outputs)
# no valid anchors
if any([labels is None for labels in all_labels]):
return None
# sampled anchors of all images
num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list])
num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list])
# split targets to a list w.r.t. multiple levels
anchors_list = images_to_levels(all_anchors, num_level_anchors)
labels_list = images_to_levels(all_labels, num_level_anchors)
label_weights_list = images_to_levels(all_label_weights,
num_level_anchors)
bbox_targets_list = images_to_levels(all_bbox_targets,
num_level_anchors)
bbox_weights_list = images_to_levels(all_bbox_weights,
num_level_anchors)
return (anchors_list, labels_list, label_weights_list,
bbox_targets_list, bbox_weights_list, num_total_pos,
num_total_neg)
def loss(self,
cls_scores,
bbox_preds,
centernesses,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute losses of the head.
Args:
cls_scores (list[Tensor]): Box scores for each scale level
Has shape (N, num_anchors * num_classes, H, W)
bbox_preds (list[Tensor]): Box energies / deltas for each scale
level with shape (N, num_anchors * 4, H, W)
centernesses (list[Tensor]): Centerness for each scale
level with shape (N, num_anchors * 1, H, W)
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (list[Tensor] | None): specify which bounding
boxes can be ignored when computing the loss.
Returns:
dict[str, Tensor]: A dictionary of loss components.
"""
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == self.anchor_generator.num_levels
device = cls_scores[0].device
anchor_list, valid_flag_list = self.get_anchors(featmap_sizes,
img_metas,
device=device)
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
cls_reg_targets = self.get_targets(
anchor_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels)
if cls_reg_targets is None:
return None
(anchor_list, labels_list, label_weights_list, bbox_targets_list,
bbox_weights_list, num_total_pos, num_total_neg) = cls_reg_targets
# num_total_samples = torch.tensor(num_total_pos).item()
num_total_samples = num_total_pos
num_total_samples = max(num_total_samples, 1.0)
losses_cls, losses_bbox, loss_centerness, \
bbox_avg_factor = multi_apply(
self.loss_single,
anchor_list,
cls_scores,
bbox_preds,
centernesses,
labels_list,
label_weights_list,
bbox_targets_list,
num_total_samples=num_total_samples)
bbox_avg_factor = sum(bbox_avg_factor)
bbox_avg_factor = bbox_avg_factor.item()
if bbox_avg_factor < EPS:
bbox_avg_factor = 1
losses_bbox = list(map(lambda x: x / bbox_avg_factor, losses_bbox))
return dict(loss_cls=losses_cls,
loss_bbox=losses_bbox,
loss_centerness=loss_centerness)
def loss(self,
cls_scores,
bbox_preds,
iou_preds,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute losses of the head.
Args:
cls_scores (list[Tensor]): Box scores for each scale level
Has shape (N, num_anchors * num_classes, H, W)
bbox_preds (list[Tensor]): Box energies / deltas for each scale
level with shape (N, num_anchors * 4, H, W)
iou_preds (list[Tensor]): iou_preds for each scale
level with shape (N, num_anchors * 1, H, W)
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (list[Tensor] | None): Specify which bounding
boxes can be ignored when are computing the loss.
Returns:
dict[str, Tensor]: A dictionary of loss gmm_assignment.
"""
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == self.anchor_generator.num_levels
device = cls_scores[0].device
anchor_list, valid_flag_list = self.get_anchors(featmap_sizes,
img_metas,
device=device)
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
cls_reg_targets = self.get_targets(
anchor_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels,
)
(labels, labels_weight, bboxes_target, bboxes_weight, pos_inds,
pos_gt_index) = cls_reg_targets
cls_scores = levels_to_images(cls_scores)
cls_scores = [
item.reshape(-1, self.cls_out_channels) for item in cls_scores
]
bbox_preds = levels_to_images(bbox_preds)
bbox_preds = [item.reshape(-1, 4) for item in bbox_preds]
iou_preds = levels_to_images(iou_preds)
iou_preds = [item.reshape(-1, 1) for item in iou_preds]
pos_losses_list, = multi_apply(self.get_pos_loss, anchor_list,
cls_scores, bbox_preds, labels,
labels_weight, bboxes_target,
bboxes_weight, pos_inds)
with torch.no_grad():
labels, label_weights, bbox_weights, num_pos = multi_apply(
self.paa_reassign,
pos_losses_list,
labels,
labels_weight,
bboxes_weight,
pos_inds,
pos_gt_index,
anchor_list,
)
num_pos = sum(num_pos)
# convert all tensor list to a flatten tensor
cls_scores = torch.cat(cls_scores, 0).view(-1, cls_scores[0].size(-1))
bbox_preds = torch.cat(bbox_preds, 0).view(-1, bbox_preds[0].size(-1))
iou_preds = torch.cat(iou_preds, 0).view(-1, iou_preds[0].size(-1))
labels = torch.cat(labels, 0).view(-1)
flatten_anchors = torch.cat(
[torch.cat(item, 0) for item in anchor_list])
labels_weight = torch.cat(labels_weight, 0).view(-1)
bboxes_target = torch.cat(bboxes_target,
0).view(-1, bboxes_target[0].size(-1))
pos_inds_flatten = ((labels >= 0)
&
(labels < self.num_classes)).nonzero().reshape(-1)
losses_cls = self.loss_cls(cls_scores,
labels,
labels_weight,
avg_factor=max(num_pos, len(img_metas)))
if num_pos:
pos_bbox_pred = self.bbox_coder.decode(
flatten_anchors[pos_inds_flatten],
bbox_preds[pos_inds_flatten])
pos_bbox_target = bboxes_target[pos_inds_flatten]
iou_target = bbox_overlaps(pos_bbox_pred.detach(),
pos_bbox_target,
is_aligned=True)
losses_iou = self.loss_centerness( # iou预测分支
iou_preds[pos_inds_flatten],
iou_target.unsqueeze(-1),
avg_factor=num_pos)
losses_bbox = self.loss_bbox(pos_bbox_pred,
pos_bbox_target,
iou_target.clamp(min=eps),
avg_factor=iou_target.sum())
else:
losses_iou = iou_preds.sum() * 0
losses_bbox = bbox_preds.sum() * 0
return dict(loss_cls=losses_cls,
loss_bbox=losses_bbox,
loss_iou=losses_iou)
def get_targets(self,
anchor_list,
valid_flag_list,
gt_bboxes_list,
img_metas,
gt_bboxes_ignore_list=None,
gt_labels_list=None,
label_channels=1,
unmap_outputs=True,
return_sampling_results=False):
"""Compute regression and classification targets for anchors in
multiple images.
Args:
anchor_list (list[list[Tensor]]): Multi level anchors of each
image. The outer list indicates images, and the inner list
corresponds to feature levels of the image. Each element of
the inner list is a tensor of shape (num_anchors, 4).
valid_flag_list (list[list[Tensor]]): Multi level valid flags of
each image. The outer list indicates images, and the inner list
corresponds to feature levels of the image. Each element of
the inner list is a tensor of shape (num_anchors, )
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
img_metas (list[dict]): Meta info of each image.
gt_bboxes_ignore_list (list[Tensor]): Ground truth bboxes to be
ignored.
gt_labels_list (list[Tensor]): Ground truth labels of each box.
label_channels (int): Channel of label.
unmap_outputs (bool): Whether to map outputs back to the original
set of anchors.
Returns:
tuple: Usually returns a tuple containing learning targets.
- labels_list (list[Tensor]): Labels of each level.
- label_weights_list (list[Tensor]): Label weights of each \
level.
- bbox_targets_list (list[Tensor]): BBox targets of each level.
- bbox_weights_list (list[Tensor]): BBox weights of each level.
- num_total_pos (int): Number of positive samples in all \
images.
- num_total_neg (int): Number of negative samples in all \
images.
additional_returns: This function enables user-defined returns from
`self._get_targets_single`. These returns are currently refined
to properties at each feature map (i.e. having HxW dimension).
The results will be concatenated after the end
"""
num_imgs = len(img_metas)
assert len(anchor_list) == len(valid_flag_list) == num_imgs
# 将多层的anchor数据concat,变成一个大矩阵，方便后面计算；也就是相当于只有一个预测输出层
# anchor number of multi levels
num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]]
# concat all level anchors to a single tensor
concat_anchor_list = []
concat_valid_flag_list = []
for i in range(num_imgs):
assert len(anchor_list[i]) == len(valid_flag_list[i])
concat_anchor_list.append(torch.cat(anchor_list[i]))
concat_valid_flag_list.append(torch.cat(valid_flag_list[i]))
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
if gt_labels_list is None:
gt_labels_list = [None for _ in range(num_imgs)]
results = multi_apply(
self._get_targets_single,
concat_anchor_list,
concat_valid_flag_list,
gt_bboxes_list,
gt_bboxes_ignore_list,
gt_labels_list,
img_metas,
label_channels=label_channels,
unmap_outputs=unmap_outputs,
num_level_anchors=num_level_anchors)
(all_labels, all_label_weights, all_bbox_targets, all_bbox_weights,
pos_inds_list, neg_inds_list, sampling_results_list) = results[:7]
rest_results = list(results[7:]) # user-added return values
# no valid anchors
if any([labels is None for labels in all_labels]):
return None
# sampled anchors of all images
num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list])
num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list])
# split targets to a list w.r.t. multiple levels
# 前面把多个层的target合并了，现在还原到各自的层上面
labels_list = images_to_levels(all_labels, num_level_anchors)
label_weights_list = images_to_levels(all_label_weights,
num_level_anchors)
bbox_targets_list = images_to_levels(all_bbox_targets,
num_level_anchors)
bbox_weights_list = images_to_levels(all_bbox_weights,
num_level_anchors)
res = (labels_list, label_weights_list, bbox_targets_list,
bbox_weights_list, num_total_pos, num_total_neg)
if return_sampling_results:
res = res + (sampling_results_list,)
for i, r in enumerate(rest_results): # user-added return values
rest_results[i] = images_to_levels(r, num_level_anchors)
return res + tuple(rest_results)
def loss(self,
cls_scores,
pts_preds_init,
pts_preds_refine,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == len(self.point_generators)
device = cls_scores[0].device
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
# 为特征图上面每个点生成原图xy坐标，同时判断是否valid
center_list, valid_flag_list = self.get_points(featmap_sizes,
img_metas, device)
# 此时可以得到特征图上每个预测offset在原图上面的坐标了，相当于进行了还原操作
# 后面就容易变成bbox了
pts_coordinate_preds_init = self.offset_to_pts(center_list,
pts_preds_init)
if self.train_cfg.init.assigner['type'] == 'PointAssigner': # 默认
# Assign target for center list
candidate_list = center_list
else:
# transform center list to bbox list and
# assign target for bbox list
bbox_list = self.centers_to_bboxes(center_list)
candidate_list = bbox_list
# 设置初始loss计算所需要的targets,此时没有分类分支
cls_reg_targets_init = self.get_targets(
candidate_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
stage='init',
label_channels=label_channels)
(*_, bbox_gt_list_init, candidate_list_init, bbox_weights_list_init,
num_total_pos_init, num_total_neg_init) = cls_reg_targets_init
num_total_samples_init = (num_total_pos_init + num_total_neg_init
if self.sampling else num_total_pos_init)
# 和前面操作完全相同
center_list, valid_flag_list = self.get_points(featmap_sizes,
img_metas, device)
# 此时可以得到特征图上每个预测offset在原图上面的坐标了，相当于进行了还原操作
pts_coordinate_preds_refine = self.offset_to_pts(
center_list, pts_preds_refine)
bbox_list = []
for i_img, center in enumerate(center_list):
bbox = []
# 为啥不直接用pts_coordinate_preds_init作为bbox，还重新算一遍？
for i_lvl in range(len(pts_preds_refine)):
bbox_preds_init = self.points2bbox(
pts_preds_init[i_lvl].detach())
bbox_shift = bbox_preds_init * self.point_strides[i_lvl]
bbox_center = torch.cat(
[center[i_lvl][:, :2], center[i_lvl][:, :2]], dim=1)
# 其预测得到的bbox，作为下一个阶段的anchor
bbox.append(bbox_center +
bbox_shift[i_img].permute(1, 2, 0).reshape(-1, 4))
bbox_list.append(bbox)
cls_reg_targets_refine = self.get_targets(
bbox_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
stage='refine',
label_channels=label_channels)
(labels_list, label_weights_list, bbox_gt_list_refine,
candidate_list_refine, bbox_weights_list_refine, num_total_pos_refine,
num_total_neg_refine) = cls_reg_targets_refine
num_total_samples_refine = (num_total_pos_refine + num_total_neg_refine
if self.sampling else num_total_pos_refine)
# compute loss
losses_cls, losses_pts_init, losses_pts_refine = multi_apply(
self.loss_single,
cls_scores,
pts_coordinate_preds_init,
pts_coordinate_preds_refine,
labels_list,
label_weights_list,
bbox_gt_list_init,
bbox_weights_list_init,
bbox_gt_list_refine,
bbox_weights_list_refine,
self.point_strides,
num_total_samples_init=num_total_samples_init,
num_total_samples_refine=num_total_samples_refine)
loss_dict_all = {
'loss_cls': losses_cls,
'loss_pts_init': losses_pts_init,
'loss_pts_refine': losses_pts_refine
}
return loss_dict_all
def get_targets(self,
proposals_list,
valid_flag_list,
gt_bboxes_list,
img_metas,
gt_bboxes_ignore_list=None,
gt_labels_list=None,
stage='init',
label_channels=1,
unmap_outputs=True):
"""Compute corresponding GT box and classification targets for
proposals.
Args:
proposals_list (list[list]): Multi level points/bboxes of each
image.
valid_flag_list (list[list]): Multi level valid flags of each
image.
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
img_metas (list[dict]): Meta info of each image.
gt_bboxes_ignore_list (list[Tensor]): Ground truth bboxes to be
ignored.
gt_bboxes_list (list[Tensor]): Ground truth labels of each box.
stage (str): `init` or `refine`. Generate target for init stage or
refine stage
label_channels (int): Channel of label.
unmap_outputs (bool): Whether to map outputs back to the original
set of anchors.
Returns:
tuple:
- labels_list (list[Tensor]): Labels of each level.
- label_weights_list (list[Tensor]): Label weights of each level. # noqa: E501
- bbox_gt_list (list[Tensor]): Ground truth bbox of each level.
- proposal_list (list[Tensor]): Proposals(points/bboxes) of each level. # noqa: E501
- proposal_weights_list (list[Tensor]): Proposal weights of each level. # noqa: E501
- num_total_pos (int): Number of positive samples in all images. # noqa: E501
- num_total_neg (int): Number of negative samples in all images. # noqa: E501
"""
assert stage in ['init', 'refine']
num_imgs = len(img_metas)
assert len(proposals_list) == len(valid_flag_list) == num_imgs
# points number of multi levels
num_level_proposals = [points.size(0) for points in proposals_list[0]]
# concat all level points and flags to a single tensor
for i in range(num_imgs):
assert len(proposals_list[i]) == len(valid_flag_list[i])
proposals_list[i] = torch.cat(proposals_list[i])
valid_flag_list[i] = torch.cat(valid_flag_list[i])
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
if gt_labels_list is None:
gt_labels_list = [None for _ in range(num_imgs)]
(all_labels, all_label_weights, all_bbox_gt, all_proposals,
all_proposal_weights, pos_inds_list,
neg_inds_list) = multi_apply(self._point_target_single,
proposals_list,
valid_flag_list,
gt_bboxes_list,
gt_bboxes_ignore_list,
gt_labels_list,
stage=stage,
label_channels=label_channels,
unmap_outputs=unmap_outputs)
# no valid points
if any([labels is None for labels in all_labels]):
return None
# sampled points of all images
num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list])
num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list])
labels_list = images_to_levels(all_labels, num_level_proposals)
label_weights_list = images_to_levels(all_label_weights,
num_level_proposals)
bbox_gt_list = images_to_levels(all_bbox_gt, num_level_proposals)
proposals_list = images_to_levels(all_proposals, num_level_proposals)
proposal_weights_list = images_to_levels(all_proposal_weights,
num_level_proposals)
return (labels_list, label_weights_list, bbox_gt_list, proposals_list,
proposal_weights_list, num_total_pos, num_total_neg)
def loss(self,
cls_scores,
bbox_preds,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute losses of the head.
Args:
cls_scores (list[Tensor]): Box scores for each scale level
Has shape (N, num_anchors * num_classes, H, W)
bbox_preds (list[Tensor]): Box energies / deltas for each scale
level with shape (N, num_anchors * 4, H, W)
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (None | list[Tensor]): specify which bounding
boxes can be ignored when computing the loss. Default: None
Returns:
dict[str, Tensor]: A dictionary of loss components.
"""
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores] # 每个层的特征图size
assert len(featmap_sizes) == self.anchor_generator.num_levels
device = cls_scores[0].device
anchor_list, valid_flag_list = self.get_anchors(
featmap_sizes, img_metas, device=device)
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
cls_reg_targets = self.get_targets(
anchor_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels)
if cls_reg_targets is None:
return None
(labels_list, label_weights_list, bbox_targets_list, bbox_weights_list,
num_total_pos, num_total_neg) = cls_reg_targets
num_total_samples = (
num_total_pos + num_total_neg if self.sampling else num_total_pos)
# anchor number of multi levels
num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]]
# concat all level anchors and flags to a single tensor
concat_anchor_list = []
for i in range(len(anchor_list)):
concat_anchor_list.append(torch.cat(anchor_list[i]))
all_anchor_list = images_to_levels(concat_anchor_list,
num_level_anchors)
losses_cls, losses_bbox = multi_apply(
self.loss_single,
cls_scores,
bbox_preds,
all_anchor_list,
labels_list,
label_weights_list,
bbox_targets_list,
bbox_weights_list,
num_total_samples=num_total_samples)
return dict(loss_cls=losses_cls, loss_bbox=losses_bbox)
def loss(self,
cls_scores,
pts_preds_init,
pts_preds_refine,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == len(self.point_generators)
device = cls_scores[0].device
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
# target for initial stage
center_list, valid_flag_list = self.get_points(featmap_sizes,
img_metas, device)
pts_coordinate_preds_init = self.offset_to_pts(center_list,
pts_preds_init)
if self.train_cfg.init.assigner['type'] == 'PointAssigner':
# Assign target for center list
candidate_list = center_list
else:
# transform center list to bbox list and
# assign target for bbox list
bbox_list = self.centers_to_bboxes(center_list)
candidate_list = bbox_list
cls_reg_targets_init = self.get_targets(
candidate_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
stage='init',
label_channels=label_channels)
(*_, bbox_gt_list_init, candidate_list_init, bbox_weights_list_init,
num_total_pos_init, num_total_neg_init) = cls_reg_targets_init
num_total_samples_init = (
num_total_pos_init +
num_total_neg_init if self.sampling else num_total_pos_init)
# target for refinement stage
center_list, valid_flag_list = self.get_points(featmap_sizes,
img_metas, device)
pts_coordinate_preds_refine = self.offset_to_pts(
center_list, pts_preds_refine)
bbox_list = []
for i_img, center in enumerate(center_list):
bbox = []
for i_lvl in range(len(pts_preds_refine)):
bbox_preds_init = self.points2bbox(
pts_preds_init[i_lvl].detach())
bbox_shift = bbox_preds_init * self.point_strides[i_lvl]
bbox_center = torch.cat(
[center[i_lvl][:, :2], center[i_lvl][:, :2]], dim=1)
bbox.append(bbox_center +
bbox_shift[i_img].permute(1, 2, 0).reshape(-1, 4))
bbox_list.append(bbox)
cls_reg_targets_refine = self.get_targets(
bbox_list,
valid_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
stage='refine',
label_channels=label_channels)
(labels_list, label_weights_list, bbox_gt_list_refine,
candidate_list_refine, bbox_weights_list_refine, num_total_pos_refine,
num_total_neg_refine) = cls_reg_targets_refine
num_total_samples_refine = (
num_total_pos_refine +
num_total_neg_refine if self.sampling else num_total_pos_refine)
# compute loss
losses_cls, losses_pts_init, losses_pts_refine = multi_apply(
self.loss_single,
cls_scores,
pts_coordinate_preds_init,
pts_coordinate_preds_refine,
labels_list,
label_weights_list,
bbox_gt_list_init,
bbox_weights_list_init,
bbox_gt_list_refine,
bbox_weights_list_refine,
self.point_strides,
num_total_samples_init=num_total_samples_init,
num_total_samples_refine=num_total_samples_refine)
loss_dict_all = {
'loss_cls': losses_cls,
'loss_pts_init': losses_pts_init,
'loss_pts_refine': losses_pts_refine
}
return loss_dict_all
